1/ If you're a fledgling #DataScientist (TM), I have some boring advice for you: work with common, canonical datasets as much as possible.
They're usually canon for useful reasons.
-
Show this thread
-
2/ I'm not saying, "don't work with your [cool] dataset." If it motivates you, GREAT! But, recognize that your data may have properties that frustrate analysis in a way you don't yet understand. It's like adding moving parts to an engine. So mix cannon as much as you can.
1 reply 0 retweets 2 likesShow this thread -
Replying to @generativist
This. I tend to want to try every single method I've ever heard of on a dataset. The mother of all ensembles. Then my contraption is boil and bubble chitty chitty bang bang.
1 reply 0 retweets 1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.